arxiv

import time
import bs4
import re
from selenium import webdriver
from bs4 import BeautifulSoup as soup
driver = webdriver.Firefox()
url='https://arxiv.org/search/?query='

b1=input("enter text \n")
b2=b1.replace(" ","+")
b3='&searchtype=all&source=header'
#print(b2)
print("\n\n")
url=url+b2+b3
driver.get(url)
time.sleep(2)
refs=driver.page_source
pagesoup=soup(refs,"html.parser")
#containers=pagesoup.findAll("div",{"class":'main-section'})
containers=pagesoup.findAll("span",{"class":"abstract-full has-text-grey-dark mathjax"})
#print(containers[0].a['href'])
#print("reached contA")
i=0
#@print(containers)
#u="https://www.scienceopen.com"
for container in containers :
 # print("for loop")
  try :
   if(len(container.text)>200):
   #     i=i+1

       # print(i)
        #if(i%2!=0):

        #   driver.get(u + container['href'])
         #  refs=driver.page_source
        #   s=soup(refs,"html.parser")
          # c=s.find("div",{"itemprop":"description"})
        print(container.text)
        print("\n")
  except :
        continue
driver.close()